Information technology (IT) acceptance research has yielded many competing models, each with different sets of acceptance determinants. In this paper, we (1) review user acceptance literature and discuss eight prominent models, (2) empirically compare the eight models and their extensions, (3) formulate a unified model that integrates elements across the eight models, and (4) empirically validate the unified model. The eight models reviewed are the theory of reasoned action, the technology acceptance model, the motivational model, the theory of planned behavior, a model combining the technology acceptance model and the theory of planned behavior, the model of PC utilization, the innovation diffusion theory, and the social cognitive theory. Using data from four organizations over a six-month period with three points of measurement, the eight models explained between 17 percent and 53 percent of the variance in user intentions to use information technology. Next, a unified model, called the Unified Theory of Acceptance and Use of Technology (UTAUT), was formulated, with four core determinants of intention and usage, and up to four moderators of key relationships. UTAUT was then tested using the original data and found to outperform the eight individual models (adjusted R2 of 69 percent). UTAUT was then confirmed with data from two new organizations with similar results (adjusted R2 of 70 percent). UTAUT thus provides a useful tool for managers needing to assess the likelihood of success for new technology introductions and helps them understand the drivers of acceptance in order to proactively design interventions (including training, marketing, etc.) targeted at populations of users that may be less inclined to adopt and use new systems. The paper also makes several recommendations for future research including developing a deeper understanding of the dynamic influences studied here, refining measurement of the core constructs used in UTAUT, and understanding the organizational outcomes associated with new technology use.

User acceptance of information technology: toward a unified view

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

计量经济分析 = Econometric analysis

Attachment--and loss.

In a social network, adoption probability refers to the probability that a social entity will adopt a product, service, or opinion in the foreseeable future. Such probabilities are central to fundamental issues in social network analysis, including the influence maximization problem. In practice, adoption probabilities have significant implications for applications ranging from social network-based target marketing to political campaigns; yet, predicting adoption probabilities has not received sufficient research attention. Building on relevant social network theories, we identify and operationalize key factors that affect adoption decisions: social influence, structural equivalence, entity similarity, and confounding factors. We then develop the locally-weighted expectation-maximization method for Naive Bayesian learning to predict adoption probabilities on the basis of these factors. The principal challenge addressed in this study is how to predict adoption probabilities in the presence of confounding factors that are generally unobserved. Using data from two large-scale social networks, we demonstrate the effectiveness of the proposed method. The empirical results also suggest that cascade methods primarily using social influence to predict adoption probabilities offer limited predictive power, and that confounding factors are critical to adoption probability predictions.

https://papers.ssrn.com/sol3/Delivery.cfm/SSRN_ID2292721_code1913859.pdf?abstractid=2162209&mirid=5&type=2

Predicting Adoption Probabilities in Social Networks

Document clustering is critical to automated document management, hereby a set of documents are clustered in multiple categories, each containing similar or relevant documents. Most previous research assumes time invariability of document category; i.e., not evolving over time after creation. The adequacy of an existing category understandably may diminish as it includes influxes of new documents over time, bringing about significant changes to its content. Following an evolution-based approach to preserving user preferences in document-category management, this study extends Category Evolution (CE) technique by addressing its inherent limitations. The proposed technique (namely, CE2) automatically re-organizes document categories while taking into account those previously established by the user. We empirically evaluate the effectiveness of CE2 in different document management scenarios that are created using a set of documents from Reuters. Our evaluation includes both CE and hierarchical agglomerative clustering (HAC) for performance benchmarks. Our analysis results show CE2 to be more effective than CE and HAC, showing higher clustering recall and precision. Our findings have interesting implications to research and practice, which are discussed together with our future research directions.

/pdf/an-evolution-based-approach-to-preserving-user-preferences-3rncw37fw9.pdf

An Evolution-based Approach to Preserving User Preferences in Document-Category Management

Examining students’ learning effectiveness and satisfaction is critical to the ultimate success of technology-assisted learning that has been deployed at a fast-growing pace. The accumulated results from prior research are mostly equivocal. Based on how technologyassisted learning may influence students’ learning process, we analyze technology-assisted learning and synthesize relevant prior research, and propose a factor model that explains learning effectiveness and satisfaction. We empirically test that model with a quasiexperiment that involves 212 university students, observing their learning of Adobe Photoshop. We test the hypothesized effects of technology-assisted learning and its moderating role in influencing students’ learning effectiveness and satisfaction. According to our results, the use of technology-assisted learning adversely affects student engagement. This, in turn, negatively influences their learning effectiveness and satisfaction. Student engagement in learning activities appears to mediate the impact of technology-assisted learning on learning effectiveness. Furthermore, the influence of technology-assisted learning on learning satisfaction is mediated by both student engagement and learning effectiveness. Technology-assisted learning shows no significant moderating effects on learning effectiveness or satisfaction. Our empirical results have several important implications for technology-assisted learning research and practice.

Examining Effects of Technology-Assisted Learning on Learning Effectiveness and Satisfaction: A Quasi-Experimental Study

Service quality and cost containment represent two critical challenges in healthcare management. Toward that end, acute appendicitis, a common surgical condition, is important and requires timely, accurate diagnosis. The diverse and atypical symptoms make such diagnoses difficult, thus resulting in increased morbidity and negative appendectomy. While prior research has recognized the use of classification analysis to support acute appendicitis diagnosis, the skewed distribution of the cases pertaining to positive or negative acute appendicitis has significantly constrained the effectiveness of the existing classification techniques. In this study, we develop a pre-clustering-based classification (PCC) technique to address the skewed distribution problem common to acute appendicitis diagnosis. We empirically evaluate the proposed PCC technique with 574 clinical cases of positive and negative acute appendicitis obtained from a tertiary medical center in Taiwan. Our evaluation includes tradition support vector machine, a prevalent resampling classification technique, Alvarado scoring system, and a multi-classifier committee for performance benchmark purposes. Our results show the PCC technique more effective and less biased than the benchmark techniques, without favoring the positive or negative class.

https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1117&context=pacis2010

Supporting Acute Appendicitis Diagnosis: A Pre-Clustering-Based Classification Technique

Acceptance of information technology by targeted users has been examined considerably by previous information systems (IS) research. A review of extant literature suggests a focus on the effects of important individual differences, such as attitidinal beliefs, perceptions, basic computer skills, gender, and age. Several theoretical models or frameworks prevail and have been empirically tested using various technologies and/or organizational contexts. Few studies (if any) have investigated the impact of an individual’s cognitive style on his or her technology acceptance decision. The current research discusses the relationship between cognitive style and technology acceptance and empirically tests hypotheses it suggests. We anchor our analysis using the KAI cognitive theory (Kirtons 1977) and conducts a survey study to test the effect of cognitive style on the individual’s decision on whether to accept a new technology. We synthesize relevant previous research and propose a factor model that explains or predicts technology acecptance by targeted university students. Our model encompasses the effect of cognitive styl and includes other important acceptance drivers, and is tested empirically using the evaluative respeonses to Microsoft ACCESS by 428 undergraduate students. An investigative locus of our study is comparing the responses by innvotors and adapters. We observe that cognitive style to have a significant effect on the individual’s technology acceptance decision-making, and that innovators are more likely to accept a new technology than adaptors. Using the subjects’ responses, we test the model as a whole as well as the hypotheses it suggests. Based on our data analysis, we highlight our important findings and discuss their implications to user acceptance research as well as the practices for fostering use of information technology by university students.

/pdf/examining-effects-of-cognitive-style-on-technology-2at4n88l80.pdf

Paul Jen-Hwa Hu

Papers

Predicting Adoption Probabilities in Social Networks

An Evolution-based Approach to Preserving User Preferences in Document-Category Management

Examining Effects of Technology-Assisted Learning on Learning Effectiveness and Satisfaction: A Quasi-Experimental Study

Supporting Acute Appendicitis Diagnosis: A Pre-Clustering-Based Classification Technique

Examining Effects of Cognitive Style on Technology Acceptance Decisions